Upload trainer_state.json
Browse files- trainer_state.json +133 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 9370,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 2.83991462113127e-05,
|
| 13 |
+
"loss": 2.2891,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 2.67982924226254e-05,
|
| 19 |
+
"loss": 1.6592,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 2.51974386339381e-05,
|
| 25 |
+
"loss": 1.5543,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.43,
|
| 30 |
+
"learning_rate": 2.35965848452508e-05,
|
| 31 |
+
"loss": 1.4893,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.53,
|
| 36 |
+
"learning_rate": 2.1995731056563503e-05,
|
| 37 |
+
"loss": 1.4366,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.64,
|
| 42 |
+
"learning_rate": 2.0394877267876203e-05,
|
| 43 |
+
"loss": 1.4089,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.75,
|
| 48 |
+
"learning_rate": 1.8794023479188903e-05,
|
| 49 |
+
"loss": 1.3842,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.85,
|
| 54 |
+
"learning_rate": 1.7193169690501603e-05,
|
| 55 |
+
"loss": 1.3476,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.96,
|
| 60 |
+
"learning_rate": 1.5592315901814302e-05,
|
| 61 |
+
"loss": 1.315,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.07,
|
| 66 |
+
"learning_rate": 1.3991462113127e-05,
|
| 67 |
+
"loss": 1.1069,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.17,
|
| 72 |
+
"learning_rate": 1.23906083244397e-05,
|
| 73 |
+
"loss": 0.9875,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.28,
|
| 78 |
+
"learning_rate": 1.0789754535752402e-05,
|
| 79 |
+
"loss": 0.9898,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.39,
|
| 84 |
+
"learning_rate": 9.188900747065102e-06,
|
| 85 |
+
"loss": 0.9846,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.49,
|
| 90 |
+
"learning_rate": 7.588046958377802e-06,
|
| 91 |
+
"loss": 0.95,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.6,
|
| 96 |
+
"learning_rate": 5.987193169690502e-06,
|
| 97 |
+
"loss": 0.9333,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.71,
|
| 102 |
+
"learning_rate": 4.386339381003202e-06,
|
| 103 |
+
"loss": 0.9367,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.81,
|
| 108 |
+
"learning_rate": 2.785485592315902e-06,
|
| 109 |
+
"loss": 0.9698,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.92,
|
| 114 |
+
"learning_rate": 1.1846318036286021e-06,
|
| 115 |
+
"loss": 0.9228,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.0,
|
| 120 |
+
"step": 9370,
|
| 121 |
+
"total_flos": 2.2033587715006464e+16,
|
| 122 |
+
"train_loss": 1.2479621520800677,
|
| 123 |
+
"train_runtime": 4558.2109,
|
| 124 |
+
"train_samples_per_second": 24.666,
|
| 125 |
+
"train_steps_per_second": 2.056
|
| 126 |
+
}
|
| 127 |
+
],
|
| 128 |
+
"max_steps": 9370,
|
| 129 |
+
"num_train_epochs": 2,
|
| 130 |
+
"total_flos": 2.2033587715006464e+16,
|
| 131 |
+
"trial_name": null,
|
| 132 |
+
"trial_params": null
|
| 133 |
+
}
|